Gradient-Descent-Based IMM Smoothing for AIS Trajectory Reconstruction

Vessel trajectory information plays a critical role in vessel traffic management systems by enhancing navigational safety. However, trajectory reconstruction remains challenging due to the inherent noise and incompleteness in automatic identification system (AIS) measurements. In this paper, we propose non-homogeneous Markov chain driven interacting multiple model (NHMC-IMM), which is a novel adaptive information fusion approach by integrating multiple motion models to adapt to the diversity of target motion. The gradient descent algorithm is applied to the improved IMM, which is used to adjust the covariance matrix of the process noise and the measurement noise during the execution of the IMM. In this way, the accuracy of the model estimation is improved by updating the parameters continuously and iteratively under the given conditions of the observed measurement data, and the optimal parameters will be selected at the end of the iteration, thus enhancing the accuracy of trajectory reconstruction. To validate the effectiveness of the proposed method, experiments were conducted using AIS datasets from the coastal regions of the United States and Denmark, under varying levels of local measurement missingness. Results demonstrate superior accuracy and robustness in trajectory reconstruction, highlighting the method’s potential for improving maritime measurement systems and enhancing situational awareness.